Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it delivers real behavioral disclosure: 'counts against the org's monthly pool' (quota cost), 'Waits up to wait_ms for the answer and says so if it is still being produced' (async/latency behavior), and 'Covers the org's recent window across every stream' (scope). It stops short of stating auth requirements or explicit non-mutating guarantees, though 'READ' implies read-only.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with no filler: purpose first, then audience semantics, then scope/cost/wait behavior. The cost and async behaviors are packed into the back half efficiently. Nothing is redundant with the schema; the backtick-delimited parameter references keep it scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, no annotations, and zero required parameters, the description covers purpose, scope, audience, quota impact, and wait behavior — a strong package. The gap is that the return value is never described beyond 'the same reading the console shows', and error cases are unaddressed, leaving some inference to the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so the baseline is 3, but the description adds genuine meaning: it explains audience (technical = engineer fixing it, executive = C-suite) and gives wait_ms behavioral context (waits, then reports if still producing). Only force is left to the schema, which already describes it adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb+resource pair ('READ the bench') and clearly states the outcome: what happened, whether it matters, and what to do next. It reads distinctly from siblings like tail_logs and search_logs (raw retrieval) versus this interpretive analysis, though it never names a sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: 'the same reading the console shows' suggests when to call it, and the audience parameter hints at the consumer ('engineer fixing it' vs 'C-suite reading'). But no alternatives or exclusion conditions are named — an agent gets no explicit guidance on when to choose this over search_logs, tail_logs, or agent_report.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.